CN106776948B - Method for extracting characteristic line of track line group - Google Patents

Method for extracting characteristic line of track line group Download PDF

Info

Publication number
CN106776948B
CN106776948B CN201611097011.1A CN201611097011A CN106776948B CN 106776948 B CN106776948 B CN 106776948B CN 201611097011 A CN201611097011 A CN 201611097011A CN 106776948 B CN106776948 B CN 106776948B
Authority
CN
China
Prior art keywords
lines
line
track
trajectory
node
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN201611097011.1A
Other languages
Chinese (zh)
Other versions
CN106776948A (en
Inventor
杨昆
王加胜
王嘉学
朱彦辉
杨扬
罗毅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yunnan Normal University
Original Assignee
Yunnan Normal University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yunnan Normal University filed Critical Yunnan Normal University
Priority to CN201611097011.1A priority Critical patent/CN106776948B/en
Publication of CN106776948A publication Critical patent/CN106776948A/en
Application granted granted Critical
Publication of CN106776948B publication Critical patent/CN106776948B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29Geographical information databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a method for extracting characteristic lines of a track line group, which belongs to the technical field of track analysis and aims to solve the problems that a method for extracting characteristic lines of a plurality of track lines is complex and the existing method is not suitable for extracting intersecting track lines. The method comprises the following steps: firstly, the method comprises the following steps: calculating the distance between every two track lines in the track line group; II, secondly: taking two trajectory lines corresponding to the maximum distance in the calculated distances, and acquiring central lines of the two trajectory lines; thirdly, the method comprises the following steps: replacing the two corresponding track lines with the obtained central line, updating the track line group, judging whether the number of the track lines in the track line group is 2, if so, turning to four, and if not, turning to one; fourthly, the method comprises the following steps: and acquiring the central lines of the two track lines in the track line group, wherein the central lines are the characteristic lines of the track line group. The invention extracts the characteristic lines representing the geometric attributes of the space position, the shape, the size, the distribution and the like of a group of trajectory lines, and is beneficial to the aspects of updating and maintaining road information, analyzing main sea routes, analyzing the behavior characteristics of moving objects and the like.

Description

Method for extracting characteristic line of track line group
Technical Field
The invention relates to a method for extracting a characteristic line of a track line group, in particular to a method for extracting a characteristic line of a track line group based on a triangulation network, and belongs to the technical field of track analysis.
Background
The trajectory line is a broken line formed by recording space positions of a moving object at certain time intervals, representing the positions into trajectory points according to longitude and latitude coordinates and sequentially connecting the trajectory points according to time sequence. The characteristic line of a set of trajectory lines refers to a broken line capable of representing spatial characteristics such as spatial position, shape, size, distribution and the like reflected by all trajectory lines in the trajectory line set. The characteristic lines of the two trajectory lines are their center lines, and the calculation of the characteristic lines of the plurality of trajectory lines is complicated. The characteristic lines of the track line group can be used for updating and maintaining road information, analyzing main sea routes, analyzing behavior characteristics of moving objects and the like.
However, the current characteristic line analysis method usually divides the trajectory into line segments and then calculates the line segments, which has certain limitations. If the solution of a group of trajectory characteristic lines is converted into the solution of the center lines of two trajectory lines, most of the existing center line calculation methods aim at lines with disjoint space, and when a large number of center lines are extracted, the calculation amount is large, so that the method is not suitable for the calculation of trajectory line groups.
Disclosure of Invention
The invention aims to solve the problems that a method for extracting characteristic lines of a plurality of trajectory lines is complex and the existing method is not suitable for extracting intersecting trajectory lines.
The invention discloses a method for extracting a characteristic line of a track line group, which comprises the following steps:
the method comprises the following steps: calculating the distance between every two track lines in the track line group;
step two: taking two trajectory lines corresponding to the maximum distance in the calculated distances, and acquiring central lines of the two trajectory lines;
step three: replacing the two corresponding track lines with the obtained central line, updating the track line group, judging whether the number of the track lines in the track line group is 2, if so, turning to the fourth step, and if not, turning to the first step;
step four: and acquiring the central lines of the two track lines in the track line group, wherein the central lines are the characteristic lines of the track line group.
Preferably, in the second step, the method for acquiring the center lines of the two trajectory lines includes:
based on the triangulation network, the center lines of the two trajectory lines are acquired.
Preferably, the method for acquiring the center lines of the two trajectory lines based on the triangulation network includes:
b1, judging whether the directions of the two track lines are consistent, if so, turning to b2, and if not, reversely arranging the point set of one track line to ensure that the directions of the two track lines are consistent;
step b2, sequentially acquiring point sets forming two trajectory lines, wherein the point sets respectively are L1And L2The number of nodes in the two point sets is M and N:
Figure BDA0001169810900000021
step b3, connecting the initial nodes of the two track lines to obtain a line segment P11P21Segment P11P21Is taken as the starting point of the central line and is added into a central line point set LcPerforming the following steps;
step b4, from line segment P11P21Starting, a set of points L is taken in order1And L2Constructing a triangle by corresponding nodes, and acquiring center line points:
step b 41: with node P1iNode P2jAs a starting point, take node P1(i+1)Node P2(j+1)Judging the line segment P1iP1(i+1)And line segment P2jP2(j+1)If not, go to step b 42; if yes, the step b43 is carried out;
step b 42: constructing a triangle, comparing the line segments P1iP2(j+1)And P2jP1(i+1)Selecting the middle point of the line segment with shorter length to be added into the central line point set LcIn, go to step 44;
step b 43: obtaining a triangle P according to the intersection point Q of the two line segments1iP2jQ and triangle QP1(i+1)P2(j+1)Comparing the line segments QP separately1iAnd QP2jLine segment QP1(i+1)And QP2(j+1)The length of the central line point set L is obtained by taking points of the compared shorter line segments on the corresponding longer line segments to construct an isosceles triangle and adding the middle point of the bottom edge of the constructed isosceles triangle into the central line point set LcTurning to step b 44;
step b 44: when node P1(i+1)Participating in the construction of a triangle to obtain a midpoint, making j equal to j +1, and proceeding to step b41, when the node P is2(j+1)Participating in the construction of the triangle to obtain the midpoint, i is i +1, and the process proceeds to step b41 until the point set L1And L2All the nodes in the node list are taken out;
step b5, adding the centerline point set LcSequentially connects the center line point sets LcAnd (5) obtaining a broken line which is the central line of the two track lines.
Preferably, in the step b1, the method for determining whether the two trajectory directions are consistent includes:
taking the initial node pointing to the final node of the trajectory as the direction vectors of the trajectory, wherein the direction vectors of the two trajectories are a and b respectively, the included angle of the a and the b is theta, if the cosine value of the included angle theta is less than 0, the directions are inconsistent, otherwise, the directions are consistent, and the cosine value of the vector included angle theta is as follows:
Figure BDA0001169810900000022
preferably, in the first step, the method for calculating the distance between two trajectory lines includes:
step a 1: sequentially acquiring point sets forming two trajectory lines as L respectively1And L2The number of nodes in the two point sets is M and N:
Figure BDA0001169810900000031
step a2, calculating L in sequence1In each node P1iTo L2Each line segment P2jP2(j+1)Distance d of1ijWherein i is 1, 2, …, M, j is 1, 2, …, N-1;
step a 3: calculating L in turn2In each node P2jTo L1Each line segment P1iP1(i+1)Distance d of2ijWherein i is 1, 2, …, M-1, j is 1, 2, …, N;
step a 4: obtaining the distance D between the two track lines according to the following formula:
Figure BDA0001169810900000032
the method has the advantages that the distance between every two trajectory lines is calculated, the two trajectory lines with the largest distance are selected, the central lines of the two trajectory lines are extracted, the two trajectory lines selected are replaced in the original trajectory line group by the central lines, the trajectory lines are selected, the central lines are calculated and replaced by the same method, and the central lines of the two broken lines are the characteristic lines to be calculated when only two broken lines are left in the trajectory line group. The invention provides a method for calculating the distance between characteristic line trajectory lines, calculating the central lines of two trajectory lines and iteratively solving the characteristic lines. By applying the method, the characteristic lines representing the geometric attributes of a group of trajectory lines such as spatial position, shape, size, distribution and the like can be extracted, and the method is used as a spatial data mining method and is beneficial to the aspects of updating and maintaining road information, analyzing main sea routes, analyzing behavior characteristics of moving objects and the like.
Drawings
FIG. 1 is a diagram of a track wire set according to an embodiment.
FIG. 2 is a schematic diagram of the centerline extraction of two trajectory lines in the example.
FIG. 3 is a schematic diagram of an embodiment of a process for iteratively calculating a centerline for a track line group.
Fig. 4 is a diagram illustrating a result of extracting a trajectory line group in an embodiment.
Detailed Description
The method for extracting feature lines from a trajectory line group according to this embodiment includes the following steps:
the method comprises the following steps: calculating the distance between every two track lines in the track line group;
step two: taking two trajectory lines corresponding to the maximum distance in the calculated distances, and acquiring central lines of the two trajectory lines;
step three: replacing the two corresponding track lines with the obtained central line, updating the track line group, judging whether the number of the track lines in the track line group is 2, if so, turning to the fourth step, and if not, turning to the first step;
step four: and acquiring the central lines of the two track lines in the track line group, wherein the central lines are the characteristic lines of the track line group.
This embodiment provides a method for extracting a feature line of a trajectory line group having more than two trajectory lines, which replaces the trajectory lines having a large distance by using center lines representing features of the two trajectory lines, and narrows a range of a trajectory line characteristic line by replacing the trajectory lines having a large distance: from sparse to dense trajectory distribution. Finally, the most representative central line, namely the characteristic line is determined.
In a preferred embodiment, in the second step, the method for obtaining the center lines of the two trajectory lines includes:
and acquiring the central lines of the two track lines based on the constructed triangulation network.
In the embodiment, the track line is divided into a plurality of nodes, each node and an adjacent node form a line segment, a triangular net is constructed by judging whether the line segments in the two track lines are intersected, the middle point of the edge constructing the triangular net is obtained, and the central line is formed by utilizing the obtained middle point.
In a preferred embodiment, the method for obtaining the center lines of the two trajectory lines based on the triangulation network comprises:
b1, judging whether the directions of the two track lines are consistent, if so, turning to b2, and if not, reversely arranging the point set of one track line to ensure that the directions of the two track lines are consistent;
step b2, sequentially acquiring point sets forming two trajectory lines, wherein the point sets respectively are L1And L2The number of nodes in the two point sets is M and N:
Figure BDA0001169810900000041
step b3, connecting the initial nodes of the two track lines to obtain a line segment P11P21Segment P11P21Is taken as the starting point of the central line and is added into a central line point set LcPerforming the following steps;
step b4, from line segment P11P21Starting, a set of points L is taken in order1And L2Middle corresponding sectionAnd (3) point building a triangle, and obtaining a center line point:
step b 41: with node P1iNode P2jAs a starting point, take node P1(i+1)Node P2(j+1)Judging the line segment P1iP1(i+1)And line segment P2jP2(j+1)If not, go to step b 42; if yes, the step b43 is carried out;
step b 42: constructing a triangle, comparing the line segments P1iP2(j+1)And P2jP1(i+1)Selecting the middle point of the line segment with shorter length to be added into the central line point set LcIn, go to step 44;
step b 43: obtaining a triangle P according to the intersection point Q of the two line segments1iP2jQ and triangle QP1(i+1)P2(j+1)Comparing the line segments QP separately1iAnd QP2jLine segment QP1(i+1)And QP2(j+1)The length of the central line point set L is obtained by taking points of the compared shorter line segments on the corresponding longer line segments to construct an isosceles triangle and adding the middle point of the bottom edge of the constructed isosceles triangle into the central line point set LcTurning to step b 44;
step b 44: when node P1(i+1)Participating in the construction of a triangle to obtain a midpoint, making j equal to j +1, and proceeding to step b41, when the node P is2(j+1)Participating in the construction of the triangle to obtain the midpoint, i is i +1, and the process proceeds to step b41 until the point set L1And L2All the nodes in the node list are taken out;
step b5, adding the centerline point set LcSequentially connects the center line point sets LcAnd (5) obtaining a broken line which is the central line of the two track lines.
The embodiment provides how to calculate the point of the corresponding central line when the line segments of the two trajectory lines are intersected and not intersected, and the central point of the isosceles triangle is calculated by constructing the isosceles triangle under the intersection condition to be used as the component of the central line.
In a preferred embodiment, in step b1, the method for determining whether the directions of the two trajectory lines are consistent comprises:
taking the initial node pointing to the final node of the trajectory as the direction vectors of the trajectory, wherein the direction vectors of the two trajectories are a and b respectively, the included angle of the a and the b is theta, if the cosine value of the included angle theta is less than 0, the directions are inconsistent, otherwise, the directions are consistent, and the cosine value of the vector included angle theta is as follows:
Figure BDA0001169810900000051
in a preferred embodiment, in the first step, the method for calculating the distance between two trajectory lines includes:
step a 1: sequentially acquiring point sets forming two trajectory lines as L respectively1And L2The number of nodes in the two point sets is M and N:
Figure BDA0001169810900000052
step a2, calculating L in sequence1In each node P1iTo L2Each line segment P2jP2(j+1)Distance d of1ijWherein i is 1, 2, …, M, j is 1, 2, …, N-1;
step a 3: calculating L in turn2In each node P2jTo L1Each line segment P1iP1(i+1)Distance d of2ijWherein i is 1, 2, …, M-1, j is 1, 2, …, N;
step a 4: obtaining the distance D between the two track lines according to the following formula:
Figure BDA0001169810900000053
example (b):
firstly, the method comprises the following steps: a group of trace lines consisting of 9 trace lines, named L respectively as shown in FIG. 1, is obtained0、L1、L2、L3、L4、L5、L6、L7、L8
II, secondly: according to the distance calculation method between the track lines, the distance between every two track lines in the track line group is calculated, and the calculation result is as follows:
Figure BDA0001169810900000061
thirdly, taking the two tracks with the maximum distance L first3And L8Building a triangular net, calculating the central line, and recording the central line as L38. Referring to fig. 2, the centerline calculation method is as follows:
1. judging whether the directions of the two trajectory lines are consistent, calculating to obtain cos theta >0, wherein the directions of the two trajectory lines are consistent without adjusting the node sequence of the trajectory lines;
2. connection P11And P21Taking the midpoint C1The first node as the centerline.
3. Line segment P11P12And P21P22Disjoint, line segments P21P12<P11P22Taking P21P12Midpoint C of2A second node as a centerline;
4、P21and P12Take part in computing midpoints, thus taking their next node P13、P22Line segment P12P13And P21P22Intersect at point J1,J1P12<J1P21As an auxiliary point F1Satisfy J1P12=J1F1And additionally J1P22<J1P13As an auxiliary point F2Satisfy J1P22=J1F2Is then P12F1Midpoint, J1、P22F2The 3 rd, 4 th and 5 th nodes C with the midpoints being central lines respectively3、C4、C5
5、P22Take part in the calculation of P13Does not participate in the computation, therefore node P is taken23、P13Line segment P12P13And P22P23Intersect at point J2,J2F2<J2P22As an auxiliary point F3Satisfy J2F2=J2F3And additionally J2P23>J2P13As an auxiliary point F4Satisfy J2P13=J2F4Is thus F2F3Midpoint, J2、P13F4The 6 th, 7 th and 8 th nodes C with the central lines as the midpoints6、C7、C8
6. And analogizing in turn, calculating nodes on the central line, and when the nodes of the two lines reach the tail end, adding P24And P16The midpoint being the last node C of the centerline17
7. Sequentially connecting central line nodes C1,C2…,C17To obtain L3And L8Central line L of38
Fourthly, with L38Replacing L in a trackline group3And L8Calculating L38With other track lines (L)0、L1、L2、L4、L5、L6、L7) The distance of (c).
And fifthly, calculating the central line of the track line with the maximum distance according to a method similar to the third step, replacing the central line by a method similar to the fourth step, and updating the distance. Such iterative computation is performed until the trajectory line group has only two broken lines, the center lines of the two broken lines are the feature lines of the original trajectory line group, and the iterative computation process is as shown in fig. 3, specifically:
s1, calculating L3And L8Center line L38Replacing the trajectory line and updating the distance;
s2, calculating L1And L5Center line L15Replacing the trajectory line and updating the distance;
s3, calculating L6And L7Center line L67Replacing the trajectory line and updating the distance;
s4, calculating L0And L4Center line L04Replacing the trajectory line and updating the distance;
s5, calculating L15And L38Center line L15-38Replacing the trajectory line and updating the distance;
s6, calculating L04And L67Center line L04-67Replacing the trajectory line and updating the distance;
s7, calculating L04-67And L2Center line L04-67-2Replacing the trajectory line and updating the distance;
s8, calculating L15-38And L04-67-2The central line is obtained by obtaining the central line of the track line group
The resulting characteristic line is shown in fig. 4.

Claims (4)

1. A track line group characteristic line extraction method is characterized in that a track line is a broken line formed by recording space positions of a moving object at certain time intervals, representing the positions into track points according to longitude and latitude coordinates and sequentially connecting the track points according to a time sequence, and the method is applied to updating and maintaining road information, analyzing main sea routes and analyzing behavior characteristic of the moving object and comprises the following steps:
the method comprises the following steps: calculating the distance between every two track lines in the track line group:
step a 1: sequentially acquiring point sets forming two trajectory lines as L respectively1And L2The number of nodes in the two point sets is M and N:
Figure FDA0002528664530000012
step a2, calculating L in sequence1In each node P1iTo L2Each line segment P2jP2(j+1)Distance d of1ijWherein i is 1, 2, …, M, j is 1, 2, …, N-1;
step a 3: calculating L in turn2In each node P2jTo L1Each line segment P1iP1(i+1)Distance d of2ijWherein i is 1, 2, …, M-1, j is 1, 2, …, N;
step a 4: obtaining the distance D between the two track lines according to the following formula:
Figure FDA0002528664530000011
step two: taking two trajectory lines corresponding to the maximum distance in the calculated distances, and acquiring central lines of the two trajectory lines;
step three: replacing the two corresponding track lines with the obtained central line, updating the track line group, judging whether the number of the track lines in the track line group is 2, if so, turning to the fourth step, and if not, turning to the first step;
step four: and acquiring the central lines of the two track lines in the track line group, wherein the central lines are the characteristic lines of the track line group.
2. The method for extracting feature lines in track line groups according to claim 1, wherein in the second step, the method for obtaining the center lines of the two track lines comprises:
based on the triangulation network, the center lines of the two trajectory lines are acquired.
3. The method for extracting feature lines from trajectory line group according to claim 2, wherein the method for obtaining the centerlines of the two trajectory lines based on triangulation comprises:
b1, judging whether the directions of the two track lines are consistent, if so, turning to b2, and if not, reversely arranging the point set of one track line to ensure that the directions of the two track lines are consistent;
step b2, sequentially acquiring point sets forming two trajectory lines, wherein the point sets respectively are L1And L2The number of nodes in the two point sets is M and N:
Figure FDA0002528664530000021
step b3, connecting the initial nodes of the two track lines to obtain a line segment P11P21Segment P11P21Is taken as the starting point of the central line and is added into a central line point set LcPerforming the following steps;
step b4, from line segment P11P21Starting, a set of points L is taken in order1And L2Constructing a triangle by corresponding nodes, and acquiring center line points:
step b 41: with node P1iNode P2jAs a starting point, take node P1(i+1)Node P2(j+1)Judging the line segment P1iP1(i+1)And line segment P2jP2(j+1)If not, go to step b 42; if yes, the step b43 is carried out;
step b 42: constructing a triangle, comparing the line segments P1iP2(j+1)And P2jP1(i+1)Selecting the middle point of the line segment with shorter length to be added into the central line point set LcIn, go to step 44;
step b 43: obtaining a triangle P according to the intersection point Q of the two line segments1iP2jQ and triangle QP1(i+1)P2(j+1)Comparing the line segments QP separately1iAnd QP2jLine segment Q P1(i+1)And Q P2(j+1)The length of the central line point set L is obtained by taking points of the compared shorter line segments on the corresponding longer line segments to construct an isosceles triangle and adding the middle point of the bottom edge of the constructed isosceles triangle into the central line point set LcTurning to step b 44;
step b 44: when node P1(i+1)Participating in the construction of a triangle to obtain a midpoint, keeping j +1 and i unchanged, and proceeding to step b41, when the node P is2(j+1)Participating in the construction of the triangle to obtain the midpoint, keeping i +1 and j unchanged, and proceeding to step b41 until the point set L1And L2All the nodes in the node list are taken out;
step b5, adding the centerline point set LcSequentially connects the center line point sets LcAnd (5) obtaining a broken line which is the central line of the two track lines.
4. The method for extracting feature lines from trajectory line groups according to claim 3, wherein in step b1, the method for determining whether the directions of the two trajectories are consistent is:
taking the initial node pointing to the final node of the trajectory as the direction vectors of the trajectory, wherein the direction vectors of the two trajectories are a and b respectively, the included angle of the a and the b is theta, if the cosine value of the included angle theta is less than 0, the directions are inconsistent, otherwise, the directions are consistent, and the cosine value of the vector included angle theta is as follows:
Figure FDA0002528664530000022
CN201611097011.1A 2016-12-02 2016-12-02 Method for extracting characteristic line of track line group Expired - Fee Related CN106776948B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611097011.1A CN106776948B (en) 2016-12-02 2016-12-02 Method for extracting characteristic line of track line group

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611097011.1A CN106776948B (en) 2016-12-02 2016-12-02 Method for extracting characteristic line of track line group

Publications (2)

Publication Number Publication Date
CN106776948A CN106776948A (en) 2017-05-31
CN106776948B true CN106776948B (en) 2020-08-25

Family

ID=58883250

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611097011.1A Expired - Fee Related CN106776948B (en) 2016-12-02 2016-12-02 Method for extracting characteristic line of track line group

Country Status (1)

Country Link
CN (1) CN106776948B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111185899B (en) * 2018-11-14 2022-05-13 苏州科瓴精密机械科技有限公司 Robot control method and robot system
CN110175539B (en) * 2019-05-10 2022-05-20 广东智媒云图科技股份有限公司 Character creating method and device, terminal equipment and readable storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104573390A (en) * 2015-01-27 2015-04-29 武汉大学 Cognitive-rule-based time-space trajectory fusion method and road network topology generating method
CN104700617A (en) * 2015-04-02 2015-06-10 武汉大学 High-precision lane information extracting method based on low-precision GPS track data
CN105893961A (en) * 2016-03-30 2016-08-24 广东中冶地理信息股份有限公司 Method for extracting road center line

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104573390A (en) * 2015-01-27 2015-04-29 武汉大学 Cognitive-rule-based time-space trajectory fusion method and road network topology generating method
CN104700617A (en) * 2015-04-02 2015-06-10 武汉大学 High-precision lane information extracting method based on low-precision GPS track data
CN105893961A (en) * 2016-03-30 2016-08-24 广东中冶地理信息股份有限公司 Method for extracting road center line

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"Topology Constrain for River Dimension-reducing Generalization in Land-use Map";Baode Jiang等;《19th International Conference on Geoinformatics》;20110626;全文 *

Also Published As

Publication number Publication date
CN106776948A (en) 2017-05-31

Similar Documents

Publication Publication Date Title
CN111882593B (en) Point cloud registration model and method combining attention mechanism and three-dimensional graph convolution network
CN106528740B (en) Road axis extracting method based on Delaunay triangulation network
CN105869173A (en) Stereoscopic vision saliency detection method
CN106023298A (en) Point cloud rigid registration method based on local Poisson curved surface reconstruction
Guo et al. Automatic crack distress classification from concrete surface images using a novel deep-width network architecture
CN102890703B (en) A kind of heterogeneous multidimensional scaling method of network
CN105137412B (en) A kind of 2D laser radars range image middle conductor feature Accurate Curve-fitting method
CN112257597A (en) Semantic segmentation method of point cloud data
CN103473388A (en) System and device capable of realizing automatic layout of flow chart
CN111858810B (en) Modeling elevation point screening method for road DEM construction
CN106776948B (en) Method for extracting characteristic line of track line group
CN111209805B (en) Rapid fusion optimization method for multi-channel segment data of lane line crowdsourcing data
CN103440683A (en) Triangular grid reconstruction method based on three-dimensional scattered dense point clouds
WO2017107865A1 (en) Image retrieval system, server, database, and related method
CN111027140A (en) Airplane standard part model rapid reconstruction method based on multi-view point cloud data
CN101986295B (en) Image clustering method based on manifold sparse coding
CN104504709A (en) Feature ball based classifying method of three-dimensional point-cloud data of outdoor scene
CN103927418A (en) Method for manufacturing meshed drainage channels of urban road drains on basis of DEM (digital elevation model)
CN114332291A (en) Oblique photography model building outer contour rule extraction method
CN101882150A (en) Three-dimensional model comparison and search method based on nuclear density estimation
CN111985414B (en) Joint position determining method and device
CN113514072B (en) Road matching method oriented to navigation data and large-scale drawing data
WO2017107866A1 (en) Image retrieval server and system, related retrieval and troubleshooting method
CN105224748B (en) A kind of section preprocess method of non-uniform beam finite element model
CN116912661A (en) Target track prediction method and system with domain generalization capability

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20200825

Termination date: 20211202

CF01 Termination of patent right due to non-payment of annual fee